A sequential module that passes timestep embeddings to the children that support it as an extra input.

A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels: t

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determini

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determinin

Implementation that supports fp16 inputs but fp32 gains/biases.

Transformer block for image-like data. First, project the input (aka embedding) and reshape to b, t, d. Then apply standard transform

A module which performs QKV attention and splits in a different order.

Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py

Uses a pretrained BERT tokenizer by huggingface. Vocab size: 30522 (?)

Uses the CLIP transformer encoder for text (from Hugging Face)

to match AttnBlock usage

A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels: t

High-level OSInsert interface. Modes ----- - ``aggressive``: ObjectStitch + SAM + InsertAnything - ``conservative``: background + bbo

Configuration for ObjectStitch inference. Parameters are intentionally minimal; more options can be added when we hook up the real model impl

A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping

Configuration for SAM-on-ObjectStitch inference.

Wraps an arbitrary object with __len__ and __getitem__ into a pytorch dataset

Uses the BERT tokenizr model and add some transformer encoder layers

The half UNet model with attention and timestep embedding. For usage, see UNet.

note: use with a base_lr of 1.0

supports repeated iterations, configurable via lists note: use with a base_lr of 1.0.

main class